Automated Detection of Cracks in Asphalt Pavement Images Using Texture Descriptors and Machine Learning Classifier

The cracks play a major role in deteriorating the transportation infrastructure. The maintenance of the pavement is done by the early diagnosis of crack. The manual approaches for evaluating a pavement is done by the experts which consumes more time and the occasionally produces subjective results. Hence an 2D digital road image is analyzed to detect the crack automatically. The proposed work focuses on the pre-processing the image, extracting the texture feature and classification using LGBM classifier. The texture descriptor explored here are Grey-level Co-occurrence matrix (GLCM), Local binary pattern (LBP), Gabor filter and their respective combinations for extracting the features on the non-overlapping image blocks (80 × 80 pixels) and a Light Gradient Boosting Machine (LGBM) algorithm to classify the image block containing a crack or not and then localizing the cracks. The experimentation was performed on the four standard dataset like Road Damage Dataset (RDD)-2018, Road Damage Dataset (RDD)-2019, Road Damage Dataset (RDD)-2020 and Road Damage Dataset (RDD)-2022 considering the different locations and uneven illumination condition. From the study it is figured out that Co-occurrence matrix of the LBP image with Light Gradient Boosting Machine (LGBM) Classifier gave good accuracy results. The accuracy for RDD-2018, RDD-2019, RDD 2020 and RDD 2022 dataset are 0.7707, 0.6778, 0.6227 and 0.6051 respectively. This proposed framework was successfully in identifying and localizing the cracks in a irregular texture background or uneven illumination in the pavement image based on the conventional machine learning approach which helps in the easy maintenance of the pavement.